Shreya Shankar: belief

Transcript context

…Amazing. Okay. What are a couple of just tips and tricks you want to leave people with as they start on their eval journey or just try to get better at something they're already doing? Tip number one is just don't be alarmed or don't be scared of looking at your data. The process, we try to make it as structured as possible. There are inevitably questions that are going to come up. That's totally fine. You might feel like you're not doing it perfectly. That's also fine. The goal is not to do evals perfectly, it's to actionably improve your product. We guarantee you, no matter what you do, if you're doing parts of these process, you're going to find ways of actionable improvement, and then you're going to iterate on your own process from there. The other tip that I would say is, we are very pro-AI. Use LLMs to help you organize any thoughts that you have throughout this entire process. This could be everything ranging from initial product requirements. Figure out how to organize them for yourself. Figure out how to improve on that product requirements doc based on the open codes that you've created. Don't be afraid to use AI in ways that present information better for you. Sweet, so don't be scared. Use LLMs as much as you can throughout the process.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.